Create README.md

# Causal Whisper

causal-whisper is an openai-whisper based streaming model.
Available on 5 differenet chunk sizes for the **english transcription**:
1. 1000[msec] (small, large-v2).
1. 300[msec] (base, small, large-v2).
1. 200[msec] (base, small, large-v2).
1. 100[msec] (base, small, large-v2).
1. 40[msec] (base, small, large-v2).

A large-v2 model is available for french, portuguese, spanish and german with a chunk size of 300[msec].

README.md

@@ -0,0 +1,21 @@
+---
+license: mit
+datasets:
+- openslr/librispeech_asr
+- facebook/multilingual_librispeech
+language:
+- en
+- fr
+- de
+- pt
+- es
+metrics:
+- wer
+base_model:
+- openai/whisper-base
+- openai/whisper-small
+- openai/whisper-large-v2
+pipeline_tag: automatic-speech-recognition
+tags:
+- streaming
+---